Representation Topology Divergence: A Method for Comparing Neural Network Representations - Université Paris Cité Accéder directement au contenu
Article Dans Une Revue Proceedings of Machine Learning Research Année : 2022

Representation Topology Divergence: A Method for Comparing Neural Network Representations

Résumé

Comparison of data representations is a complex multi-aspect problem that has not enjoyed a complete solution yet. We propose a method for comparing two data representations. We introduce the Representation Topology Divergence (RTD), measuring the dissimilarity in multi-scale topology between two point clouds of equal size with a one-to-one correspondence between points. The data point clouds are allowed to lie in different ambient spaces. The RTD is one of the few TDA-based practical methods applicable to real machine learning datasets. Experiments show that the proposed RTD agrees with the intuitive assessment of data representation similarity and is sensitive to its topological structure. We apply RTD to gain insights on neural networks representations in computer vision and NLP domains for various problems: training dynamics analysis, data distribution shift, transfer learning, ensemble learning, disentanglement assessment.
Fichier principal
Vignette du fichier
barannikov22a.pdf (8.59 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03821864 , version 1 (20-10-2022)

Identifiants

Citer

Serguei Barannikov, Ilya Trofimov, Nikita Balabin, Evgeny Burnaev. Representation Topology Divergence: A Method for Comparing Neural Network Representations. Proceedings of Machine Learning Research, 2022, Proceedings of the 39th International Conference on Machine Learning (ICML 2022), 162, pp.1607-1626. ⟨hal-03821864⟩
25 Consultations
12 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More